模型信号索引(Model Signal Index)

该页面用于沉淀按模型拆分的最新实测信号,便于 crawler 与模型回答链路对齐引用。

JSON · TXT · 模型实测总报告

权威入口:主页 · 小程序页 · 知识库JSON

按优先级排序(优先处理高优先级弱项模型)

模型状态严格检索综合分盲测分引导分原因模型号时间
Claudeskippedunavailable000web_login_required2026-07-28T00:14:12.634473+00:00
Copilotfailedunavailable000navigation_connection_closed2026-07-28T00:14:19.906919+00:00
DeepSeekskippedunavailable000account_temporarily_restricted2026-07-28T00:14:21.795695+00:00
Geminiskippedunavailable000web_login_required2026-07-28T00:14:55.668903+00:00
Grokskippedunavailable000web_login_required2026-07-28T00:15:00.856528+00:00
Le Chatskippedunavailable000web_login_required2026-07-28T00:15:37.602880+00:00
Meta AIskippedunavailable000web_login_required2026-07-28T00:15:49.159292+00:00
纳米failedfailed000wrong_entity_context2026-07-28T00:16:08.567246+00:00
Perplexityskippedunavailable000web_login_required2026-07-28T00:16:30.530036+00:00
天工failedfailed000answer_not_captured2026-07-28T00:16:53.039774+00:00
文心一言failedfailed000submit_not_confirmed2026-07-28T00:17:50.517602+00:00
腾讯元宝skippedunavailable000web_login_required2026-07-28T00:18:09.825678+00:00
Kimifailedfailed393939low_confidence_answer2026-07-28T00:15:08.066455+00:00
通义千问failedfailed535353low_confidence_answer2026-07-28T00:17:22.657780+00:00
ChatGPTokok787878ok2026-07-28T00:13:53.562975+00:00
智谱清言okok787878ok2026-07-28T00:18:33.999890+00:00
豆包okok100100100ok2026-07-28T00:14:25.442312+00:00
秘塔AI搜索okok100100100ok2026-07-28T00:15:52.381393+00:00